Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5709 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.7292. Min Act: -0.0000

Data Index: 120427 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.7663. Min Act: -0.0000

Data Index: 871294 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.5129. Min Act: -0.0000

Data Index: 1308207 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.6386. Min Act: -0.0000

Data Index: 1316807 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.6144. Min Act: -0.0000

Data Index: 1400896 (Python Code)

Max Activating Token Index: 96

Text #5

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.5022. Min Act: -0.0000

Data Index: 71871 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.3100. Min Act: -0.0000

Data Index: 1006205 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.2727. Min Act: -0.0000

Data Index: 150118 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.2552. Min Act: -0.0000

Data Index: 5676 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.2122. Min Act: -0.0000

Data Index: 1337172 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.1830. Min Act: -0.0000

Data Index: 325001 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.3272. Min Act: -0.0000

Data Index: 773217 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.2945. Min Act: -0.0000

Data Index: 1628369 (Python Code)

Max Activating Token Index: 646

Text #13

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.2920. Min Act: -0.0000

Data Index: 908365 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.1790. Min Act: -0.0000

Data Index: 772172 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.2836. Min Act: -0.0000

Data Index: 1020436 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.3773. Min Act: -0.0000

Data Index: 1200957 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.2510. Min Act: -0.0000

Data Index: 485045 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.3104. Min Act: -0.0000

Data Index: 1001776 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.2168. Min Act: -0.0000

Data Index: 898167 (C4 (Web Text))

Max Activating Token Index: 492